{"id":"https://openalex.org/W4313179182","doi":"https://doi.org/10.1109/tcds.2022.3209680","title":"A Reinforcement Learning Method for Rearranging Scattered Irregular Objects Inside a Crate","display_name":"A Reinforcement Learning Method for Rearranging Scattered Irregular Objects Inside a Crate","publication_year":2022,"publication_date":"2022-09-27","ids":{"openalex":"https://openalex.org/W4313179182","doi":"https://doi.org/10.1109/tcds.2022.3209680"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2022.3209680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3209680","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101942393","display_name":"Liang Tang","orcid":"https://orcid.org/0000-0002-2012-5367"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liang Tang","raw_affiliation_strings":["Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064641989","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0001-9292-024X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340337","display_name":"Huang Huang","orcid":"https://orcid.org/0000-0002-8662-6973"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang Huang","raw_affiliation_strings":["Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053035636","display_name":"Xinru Xie","orcid":"https://orcid.org/0000-0002-3035-0453"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinru Xie","raw_affiliation_strings":["Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108297145","display_name":"Nailong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nailong Liu","raw_affiliation_strings":["Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006122111","display_name":"Mou Li","orcid":"https://orcid.org/0000-0002-4293-0850"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mou Li","raw_affiliation_strings":["Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101942393"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6061,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67056151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"15","issue":"3","first_page":"1314","last_page":"1322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8753807544708252},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7192898392677307},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5672391057014465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511527419090271},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5035845637321472},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.44279956817626953},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4325176775455475},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4168877601623535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8753807544708252},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7192898392677307},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5672391057014465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511527419090271},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5035845637321472},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.44279956817626953},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4325176775455475},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4168877601623535},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2022.3209680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3209680","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1400328712","display_name":null,"funder_award_id":"2018AAA0102700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1989021449","https://openalex.org/W2145339207","https://openalex.org/W2194775991","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2953431737","https://openalex.org/W2962793652","https://openalex.org/W2964043796","https://openalex.org/W2967842325","https://openalex.org/W3003793997","https://openalex.org/W3004003273","https://openalex.org/W3021544315","https://openalex.org/W3035198432","https://openalex.org/W3084214343","https://openalex.org/W3090417004","https://openalex.org/W3091619233","https://openalex.org/W3113053674","https://openalex.org/W3119044505","https://openalex.org/W3131115577","https://openalex.org/W3133137374","https://openalex.org/W3133879830","https://openalex.org/W3164005523","https://openalex.org/W3176770340","https://openalex.org/W3178538552","https://openalex.org/W3186881096","https://openalex.org/W3199670492","https://openalex.org/W3200528739","https://openalex.org/W3200879008","https://openalex.org/W3205933337","https://openalex.org/W4205096660","https://openalex.org/W4213322786","https://openalex.org/W4293294484","https://openalex.org/W4300799055","https://openalex.org/W6627932998","https://openalex.org/W6692846177","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6741480351","https://openalex.org/W6747473740","https://openalex.org/W6801457775","https://openalex.org/W6801742604","https://openalex.org/W6809008344"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1601203902","https://openalex.org/W2102464536","https://openalex.org/W2361332776","https://openalex.org/W4225671779","https://openalex.org/W1568097102","https://openalex.org/W4390419160","https://openalex.org/W2897407000","https://openalex.org/W2248934910"],"abstract_inverted_index":{"Arranging":[0],"objects":[1,74,141],"from":[2],"a":[3,66,76,102,108],"random":[4],"and":[5,19,31,51,80,91,107,127,151,154],"scattered":[6,72,140],"distribution":[7],"into":[8,145],"an":[9,59,149],"integral":[10],"part":[11],"has":[12],"many":[13],"applications,":[14],"including":[15],"bin":[16],"packing,":[17],"logistics,":[18],"other":[20,147],"industrial":[21],"fields.":[22],"Measurement":[23],"noises,":[24],"manipulation":[25],"uncertainties,":[26],"models":[27],"of":[28,40,47,68],"irregular":[29,73],"objects,":[30],"rich":[32],"contacts":[33],"bring":[34],"considerable":[35],"challenges":[36],"to":[37,86,143,158],"the":[38,41,48,88,92,134,139,159],"improvements":[39],"overall":[42],"performance,":[43,90],"such":[44],"as":[45],"seamlessness":[46],"final":[49],"pattern":[50],"task":[52],"efficiency.":[53],"In":[54],"this":[55],"article,":[56],"we":[57],"propose":[58],"end-to-end":[60,116],"reinforcement":[61],"learning":[62,97],"strategy":[63],"that":[64,99,133],"generates":[65],"series":[67],"pushing":[69,89],"movements":[70],"for":[71,115],"inside":[75],"crate.":[77],"An":[78],"abstracted":[79],"sparse":[81],"reward":[82],"function":[83],"is":[84,113,122],"proposed":[85,120,135],"evaluate":[87],"proximal":[93],"policy":[94],"optimization":[95],"(PPO)":[96],"method":[98,121,136],"simultaneously":[100],"trains":[101],"convolutional":[103],"neural":[104],"network":[105,112],"(CNN)":[106],"fully":[109],"connected":[110],"actor":[111],"developed":[114],"decision":[117],"making.":[118],"The":[119,130],"evaluated":[123],"in":[124,148],"both":[125],"simulation":[126],"real-world":[128],"scenarios.":[129],"results":[131],"show":[132],"can":[137,155],"arrange":[138],"tightly":[142],"fit":[144],"each":[146],"efficient":[150],"flexible":[152],"way,":[153],"be":[156],"transferred":[157],"real":[160],"world":[161],"with":[162],"unseen":[163],"objects.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}